{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:21:45Z","timestamp":1743074505832,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819786190"},{"type":"electronic","value":"9789819786206"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8620-6_14","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"201-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-Dominant Interactive Attention for Cross-Modal Sentiment Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0916-7854","authenticated-orcid":false,"given":"Zebao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9737-8872","authenticated-orcid":false,"given":"Shuang","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9297-5662","authenticated-orcid":false,"given":"Haiwei","family":"Pan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Afzal, A.M.S.: Optimized support vector machine model for visual sentiment analysis. In: 2021 3rd International Conference on Signal Processing and Communication (ICPSC), pp. 171\u2013175. IEEE (2021)","DOI":"10.1109\/ICSPC51351.2021.9451669"},{"issue":"3","key":"14_CR2","doi-asserted-by":"publisher","first-page":"4073","DOI":"10.1007\/s11227-021-04019-5","volume":"78","author":"Q Bai","year":"2022","unstructured":"Bai, Q., Zhou, J., He, L.: PG-RNN: using position-gated recurrent neural networks for aspect-based sentiment classification. J. Supercomput. 78(3), 4073\u20134094 (2022)","journal-title":"J. Supercomput."},{"key":"14_CR3","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer (2020). arXiv:2004.05150"},{"issue":"9","key":"14_CR4","doi-asserted-by":"publisher","first-page":"12405","DOI":"10.1007\/s11042-022-12410-4","volume":"81","author":"P Bhuvaneshwari","year":"2022","unstructured":"Bhuvaneshwari, P., Rao, A.N., Robinson, Y.H., Thippeswamy, M.: Sentiment analysis for user reviews using bi-LSTM self-attention based CNN model. Multimed. Tools Appl. 81(9), 12405\u201312419 (2022)","journal-title":"Multimed. Tools Appl."},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Birjali, M., Kasri, M., Beni-Hssane, A.: A comprehensive survey on sentiment analysis: Approaches, challenges and trends. Knowl.-Based Syst. 226, 107134 (2021)","DOI":"10.1016\/j.knosys.2021.107134"},{"key":"14_CR6","unstructured":"Cao, Z., Hong, F., Wu, T., Pan, L., Liu, Z.: Large-vocabulary 3d diffusion model with transformer, pp. arXiv\u20132309 (2023)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, Y., Liu, Q.: Visual and textual sentiment analysis using deep fusion convolutional neural networks. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 1557\u20131561. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296543"},{"key":"14_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Duan, J., Chen, L., Tran, S., Yang, J., Xu, Y., Zeng, B., Chilimbi, T.: Multi-modal alignment using representation codebook. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15651\u201315660 (2022)","DOI":"10.1109\/CVPR52688.2022.01520"},{"issue":"1","key":"14_CR10","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y., et al.: A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 87\u2013110 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR11","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. Adv. Neural. Inf. Process. Syst. 34, 15908\u201315919 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Gelbukh, A., Zadeh, A., Morency, L.p., Poria, S.: Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis. In: Proceedings of the 2021 International Conference On Multimodal Interaction, pp. 6\u201315 (2021)","DOI":"10.1145\/3462244.3479919"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Huang, C., Zhang, J., Wu, X., Wang, Y., Li, M., Huang, X.: Tefna: text-centered fusion network with crossmodal attention for multimodal sentiment analysis. Knowl.-Based Syst. 269, 110502 (2023)","DOI":"10.1016\/j.knosys.2023.110502"},{"key":"14_CR14","unstructured":"Huang, Y., Tang, J., Chen, Z., Zhang, R., Zhang, X., Chen, W., Zhao, Z., Lv, T., Hu, Z., Zhang, W.: Structure-clip: enhance multi-modal language representations with structure knowledge. In: AAAI. AAAI Press (2024)"},{"key":"14_CR15","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: International conference on machine learning. pp. 5583\u20135594. PMLR (2021)"},{"key":"14_CR16","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: International Conference on Learning Representations (2019)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Krishna, D., Patil, A.: Multimodal emotion recognition using cross-modal attention and 1d convolutional neural networks. In: Interspeech, pp. 4243\u20134247 (2020)","DOI":"10.21437\/Interspeech.2020-1190"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Li, C., Xu, H., Tian, J., Wang, W., Yan, M., Bi, B., Ye, J., Chen, H., Xu, G., Cao, Z., et\u00a0al.: mplug: Effective and efficient vision-language learning by cross-modal skip-connections. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 7241\u20137259 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"14_CR19","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Lu, T., Li, Y., Yu, T., Huang, S., Zheng, H.T., Zhang, R., Yuan, J.: Mesed: a multi-modal entity set expansion dataset with fine-grained semantic classes and hard negative entities (2023)","DOI":"10.1609\/aaai.v38i8.28715"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Quan, R., Zhu, L., Yang, Y.: Efficient multimodal fusion via interactive prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2604\u20132613 (2023)","DOI":"10.1109\/CVPR52729.2023.00256"},{"key":"14_CR22","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/TASLP.2021.3049898","volume":"29","author":"Z Lian","year":"2021","unstructured":"Lian, Z., Liu, B., Tao, J.: Ctnet: conversational transformer network for emotion recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 985\u20131000 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Liang, B., Su, H., Gui, L., Cambria, E., Xu, R.: Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowl.-Based Syst. 235, 107643 (2022)","DOI":"10.1016\/j.knosys.2021.107643"},{"key":"14_CR24","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: A robustly optimized bert pretraining approach (2019). arXiv:1907.11692"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Mao, H., Yuan, Z., Xu, H., Yu, W., Liu, Y., Gao, K.: M-sena: an integrated platform for multimodal sentiment analysis. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 204\u2013213 (2022)","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Mercea, O.B., Hummel, T., Koepke, A.S., Akata, Z.: Temporal and cross-modal attention for audio-visual zero-shot learning. In: European Conference on Computer Vision, pp. 488\u2013505. Springer (2022)","DOI":"10.1007\/978-3-031-20044-1_28"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Mercea, O.B., Riesch, L., Koepke, A., Akata, Z.: Audio-visual generalised zero-shot learning with cross-modal attention and language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10553\u201310563 (2022)","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Niu, T., Zhu, S., Pang, L., El\u00a0Saddik, A.: Sentiment analysis on multi-view social data. In: MultiMedia Modeling: 22nd International Conference, MMM 2016, Miami, FL, USA, January 4-6, 2016, Proceedings, Part II 22, pp. 15\u201327. Springer (2016)","DOI":"10.1007\/978-3-319-27674-8_2"},{"key":"14_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (ICLR 2015). Computational and Biological Learning Society (2015)"},{"key":"14_CR30","unstructured":"Tang, A., Shen, L., Luo, Y., Zhan, Y., Hu, H., Du, B., Chen, Y., Tao, D.: Parameter-efficient multi-task model fusion with partial linearization. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the Conference. Association for computational linguistics. Meeting, vol.\u00a02019, p.\u00a06558. NIH Public Access (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"14_CR32","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Q., Ahmed, M., Li, Z., Pan, W., Liu, H.: Joint inference for aspect-level sentiment analysis by deep neural networks and linguistic hints. IEEE Trans. Knowl. Data Eng. 33(5), 2002\u20132014 (2019)","DOI":"10.1109\/TKDE.2019.2947587"},{"issue":"7","key":"14_CR34","doi-asserted-by":"publisher","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","volume":"55","author":"M Wankhade","year":"2022","unstructured":"Wankhade, M., Rao, A.C.S., Kulkarni, C.: A survey on sentiment analysis methods, applications, and challenges. Artif. Intell. Rev. 55(7), 5731\u20135780 (2022)","journal-title":"Artif. Intell. Rev."},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Xu, G., Liu, P., Zhu, Z., Liu, J., Xu, F.: Attention-enhanced graph convolutional networks for aspect-based sentiment classification with multi-head attention. Appl. Sci. 11(8), 3640 (2021)","DOI":"10.3390\/app11083640"},{"key":"14_CR36","unstructured":"Xu, J., Gandelsman, Y., Bar, A., Yang, J., Gao, J., Darrell, T., Wang, X.: Improv: inpainting-based multimodal prompting for computer vision tasks (2023)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W.: Multisentinet: A deep semantic network for multimodal sentiment analysis. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 2399\u20132402 (2017)","DOI":"10.1145\/3132847.3133142"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W., Chen, G.: A co-memory network for multimodal sentiment analysis. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 929\u2013932 (2018)","DOI":"10.1145\/3209978.3210093"},{"issue":"12","key":"14_CR39","doi-asserted-by":"publisher","first-page":"5412","DOI":"10.1109\/TNNLS.2020.2967597","volume":"31","author":"X Xu","year":"2020","unstructured":"Xu, X., Wang, T., Yang, Y., Zuo, L., Shen, F., Shen, H.T.: Cross-modal attention with semantic consistence for image-text matching. IEEE Trans. Neural Netw. Learn. Syst. 31(12), 5412\u20135425 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"14_CR40","doi-asserted-by":"publisher","first-page":"4335","DOI":"10.1007\/s10462-019-09794-5","volume":"53","author":"A Yadav","year":"2020","unstructured":"Yadav, A., Vishwakarma, D.K.: Sentiment analysis using deep learning architectures: a review. Artif. Intell. Rev. 53(6), 4335\u20134385 (2020)","journal-title":"Artif. Intell. Rev."},{"key":"14_CR41","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1109\/TMM.2020.3035277","volume":"23","author":"X Yang","year":"2020","unstructured":"Yang, X., Feng, S., Wang, D., Zhang, Y.: Image-text multimodal emotion classification via multi-view attentional network. IEEE Trans. Multimed. 23, 4014\u20134026 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"14_CR42","doi-asserted-by":"publisher","first-page":"2033","DOI":"10.1109\/TMM.2020.3007352","volume":"23","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Xu, M.: Weakly supervised emotion intensity prediction for recognition of emotions in images. IEEE Trans. Multimed. 23, 2033\u20132044 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhu, Y., Zhang, W., Zhu, Y.: Cross-modal image sentiment analysis via deep correlation of textual semantic. Knowl.-Based Syst. 216, 106803 (2021)","DOI":"10.1016\/j.knosys.2021.106803"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"14_CR45","unstructured":"Zhao, Z., Deng, L., Bai, H., Cui, Y., Zhang, Z., Zhang, Y., Qin, H., Chen, D., Zhang, J., Wang, P., et\u00a0al.: Image fusion via vision-language model, pp. arXiv\u20132402 (2024)"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, P., Shi, W., Tian, J., Qi, Z., Li, B., Hao, H., Xu, B.: Attention-based bidirectional long short-term memory networks for relation classification. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (volume 2: Short papers), pp. 207\u2013212 (2016)","DOI":"10.18653\/v1\/P16-2034"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8620-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:16:53Z","timestamp":1736885813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}